Reasoning Over Semantic-Level Graph for Fact Checking

Abstract

Fact checking is a challenging task because verifying the truthfulness of a claim requires reasoning about multiple retrievable evidence. In this work, we present a method suitable for reasoning about the semantic-level structure of evidence. Unlike most previous works, which typically represent evidence sentences with either string concatenation or fusing the features of isolated evidence sentences, our approach operates on rich semantic structures of evidence obtained by semantic role labeling. We propose two mechanisms to exploit the structure of evidence while leveraging the advances of pre-trained models like BERT, GPT or XLNet. Specifically, using XLNet as the backbone, we first utilize the graph structure to re-define the relative distances of words, with the intuition that semantically related words should have short distances. Then, we adopt graph convolutional network and graph attention network to propagate and aggregate information from neighboring nodes on the graph. We evaluate our system on FEVER, a benchmark dataset for fact checking, and find that rich structural information is helpful and both our graph-based mechanisms improve the accuracy. Our model is the state-of-the-art system in terms of both official evaluation metrics, namely claim verification accuracy and FEVER score.

arXiv comment9pages

References in corpus (9)

• Semi-Supervised Classification with Graph Convolutional Networks
• Enhanced LSTM for Natural Language Inference
• ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
• Simple BERT Models for Relation Extraction and Semantic Role Labeling
• Assessing The Factual Accuracy of Generated Text
• Adversarial attacks against Fact Extraction and VERification
• UKP-Athene: Multi-Sentence Textual Entailment for Claim Verification
• TwoWingOS: A Two-Wing Optimization Strategy for Evidential Claim Verification
• Improved Semantic-Aware Network Embedding with Fine-Grained Word Alignment

Cited by in corpus (5)

• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Machine Generation and Detection of Arabic Manipulated and Fake News
• LOREN: Logic-Regularized Reasoning for Interpretable Fact Verification
• CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims
• Time-Aware Evidence Ranking for Fact-Checking